fix(agent): gate MCP tool discovery on startup (#25034)

The first `/mcp/tools` request could race workspace startup and return
an empty tool list before startup scripts had a chance to write
`.mcp.json`. Chatd may only discover tools once for a turn, so that
empty response could hide workspace MCP tools even though the agent
loaded them later.

Make the manager wait for startup to settle before treating missing MCP
config files as a real empty state. Tool listing now goes through one
manager-owned path that starts reload work independently of caller
cancellation; caller contexts only bound that caller's wait. After the
first reload body settles, transient reload errors return cached tools
with the error so the HTTP handler can degrade to the last known tool
set instead of returning `[]`.

The handler is intentionally thin: it asks the manager for tools, logs
any degraded path, and still returns the tool response shape callers
already expect. Tests cover startup gating, caller-canceled waits,
manager close, reload timeout via quartz, and cached-tool fallback after
a later reload error.

agent/agent.go

@@ -1413,6 +1413,7 @@ func (a *agent) handleManifest(manifestOK *checkpoint) func(ctx context.Context,
 				// lifecycle transition to avoid delaying Ready.
 				// This runs inside the tracked goroutine so it
 				// is properly awaited on shutdown.
+				a.mcpManager.MarkStartupSettled()
 				if mcpErr := a.mcpManager.Reload(a.gracefulCtx, a.contextConfigAPI.MCPConfigFiles()); mcpErr != nil {
 					a.logger.Warn(ctx, "failed to reload workspace MCP servers", slog.Error(mcpErr))
 				}